2022-12-10 16:06:35 -08:00
2021-11-20 18:40:18 -05:00
2020-07-10 08:18:13 -04:00
2018-11-21 14:11:28 -05:00
2021-07-20 15:08:33 -04:00
2011-11-24 20:45:50 +00:00
2014-08-11 15:49:53 +00:00
2021-11-20 13:48:23 -05:00
2021-07-20 14:12:17 -04:00
2020-04-23 22:44:51 -04:00

find-object (standalone)

Linux: Build Status Windows: Build status

Find-Object project, visit the home page for more information.

find_object_2d (ROS package)

Install

Binaries:

# ROS Kinetic:
 $ sudo apt-get install ros-kinetic-find-object-2d
# ROS Jade:
 $ sudo apt-get install ros-jade-find-object-2d
# ROS Indigo:
 $ sudo apt-get install ros-indigo-find-object-2d
# ROS Hydro:
 $ sudo apt-get install ros-hydro-find-object-2d

Source:

  • If you want SURF/SIFT on Indigo/Jade/Kinetic (Hydro has already SIFT/SURF), you have to build OpenCV from source to have access to nonfree module. Install it in /usr/local (default) and the Find-Object should link with it instead of the one installed in ROS.

    • On Indigo/Jade, I recommend to use latest 2.4 version (2.4.11) and build it from source following these instructions. Find-Object can build with OpenCV3+xfeatures2d module, but find_object_2d package will have libraries conflict as cv-bridge is depending on OpenCV2. If you want OpenCV3, you should build ros vision-opencv package yourself (and all ros packages depending on it) so it can link on OpenCV3.

    • On Kinetic, I recommend to use OpenCV3+xfeatures2d module (to confirm OpenCV3 installed with ROS already includes SIFT/SURF, so no need to rebuild OpenCV). You can also install OpenCV2, but find_object_2d package will have libraries conflict as cv-bridge is depending on OpenCV3. Thus if you want OpenCV2 on Kinetic, you should build ros vision-opencv package yourself (and all ros packages depending on it) so it can link on OpenCV2.

# Install ROS Groovy/Hydro/Indigo/Jade/Kinetic (catkin build):
 $ cd ~/catkin_ws
 $ git clone https://github.com/introlab/find-object.git src/find_object_2d
 $ catkin_make

# Install ROS Fuerte (in a directory of your "ROS_PACKAGE_PATH"):
 $ svn checkout -r176 http://find-object.googlecode.com/svn/trunk/ros-pkg/find_object_2d
 $ rosmake find_object_2d

Run

 $ roscore &
 # Launch your preferred usb camera driver
 $ rosrun uvc_camera uvc_camera_node &
 $ rosrun find_object_2d find_object_2d image:=image_raw

See find_object_2d for more information.

Description
This repository contains code for detecting heat pipes in the greenhouse as well as estimating the pose of the pipes
Readme 1.4 GiB
Languages
Jupyter Notebook 93.5%
Python 4.8%
C++ 1.6%